X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FHval.pm;h=c134e297280eeff734f0a2170eeac48386c395ec;hb=96348c1a2229ffcf04153539c028f61bbe36c8b4;hp=53810b338a0cdc801a558b936e3c7c6f79dd72d2;hpb=65323f060a3db731bb9fafa004336eeb4bbb8f00;p=public-inbox.git

diff --git a/lib/PublicInbox/Hval.pm b/lib/PublicInbox/Hval.pm
index 53810b33..c134e297 100644
--- a/lib/PublicInbox/Hval.pm
+++ b/lib/PublicInbox/Hval.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2014-2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2014-2019 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 #
 # represents a header value in various forms.  Used for HTML generation
@@ -9,10 +9,13 @@ use warnings;
 use Encode qw(find_encoding);
 use PublicInbox::MID qw/mid_clean mid_escape/;
 use base qw/Exporter/;
-our @EXPORT_OK = qw/ascii_html obfuscate_addrs to_filename src_escape/;
-
+our @EXPORT_OK = qw/ascii_html obfuscate_addrs to_filename src_escape
+		to_attr from_attr/;
 my $enc_ascii = find_encoding('us-ascii');
 
+# safe-ish acceptable filename pattern for portability
+our $FN = '[a-zA-Z0-9][a-zA-Z0-9_\-\.]+[a-zA-Z0-9]'; # needs \z anchor
+
 sub new {
 	my ($class, $raw, $href) = @_;
 
@@ -29,14 +32,6 @@ sub new_msgid {
 	$class->new($msgid, mid_escape($msgid));
 }
 
-sub new_oneline {
-	my ($class, $raw) = @_;
-	$raw = '' unless defined $raw;
-	$raw =~ tr/\t\n / /s; # squeeze spaces
-	$raw =~ tr/\r//d; # kill CR
-	$class->new($raw);
-}
-
 # some of these overrides are standard C escapes so they're
 # easy-to-understand when rendered.
 my %escape_sequence = (
@@ -122,4 +117,35 @@ sub to_filename ($) {
 	$s
 }
 
+# convert a filename (or any string) to HTML attribute
+
+my %ESCAPES = map { chr($_) => sprintf('::%02x', $_) } (0..255);
+$ESCAPES{'/'} = ':'; # common
+
+sub to_attr ($) {
+	my ($str) = @_;
+
+	# git would never do this to us:
+	return if index($str, '//') >= 0;
+
+	my $first = '';
+	if ($str =~ s/\A([^A-Ya-z])//ms) { # start with a letter
+		  $first = sprintf('Z%02x', ord($1));
+	}
+	$str =~ s/([^A-Za-z0-9_\.\-])/$ESCAPES{$1}/egms;
+	$first . $str;
+}
+
+# reverse the result of to_attr
+sub from_attr ($) {
+	my ($str) = @_;
+	my $first = '';
+	if ($str =~ s/\AZ([a-f0-9]{2})//ms) {
+		$first = chr(hex($1));
+	}
+	$str =~ s!::([a-f0-9]{2})!chr(hex($1))!egms;
+	$str =~ tr!:!/!;
+	$first . $str;
+}
+
 1;